-
公开(公告)号：US06757444B2
公开(公告)日：2004-06-29
申请号：US09561780
申请日：2000-05-01
申请人： Masakazu Matsugu , Hideo Takiguchi , Koji Hatanaka
发明人： Masakazu Matsugu , Hideo Takiguchi , Koji Hatanaka
IPC分类号： G06K936
CPC分类号： H04N19/503 , H04N19/20
摘要： There is disclosed an image extraction method for extracting, from a subject image that records both the background and the object to be extracted, image data of the object using a mask. An initial mask used for extracting the subject region is generated on the basis of difference data between the subject image and the background image that records the background alone, the region of the initial mask is grown on the basis of the similarity between the features of a first region and its neighboring second region in the subject image corresponding to the initial mask, and the image data of the object is extracted from the first image on the basis of the grown mask region.
摘要翻译： 公开了一种图像提取方法，用于从使用掩模的对象的图像数据中提取记录要提取的背景和对象的对象图像。 基于用于记录背景的对象图像和背景图像之间的差分数据，生成用于提取被摄体区域的初始掩模，基于a的特征之间的相似度来生长初始掩模的区域 第一区域及其相邻的第二区域，并且基于生长的掩模区域从第一图像中提取对象的图像数据。
-
公开(公告)号：US6167167A
公开(公告)日：2000-12-26
申请号：US886076
申请日：1997-07-02
申请人： Masakazu Matsugu , Hideo Takiguchi , Koji Hatanaka
发明人： Masakazu Matsugu , Hideo Takiguchi , Koji Hatanaka
CPC分类号： H04N19/503 , H04N19/20
摘要： There is disclosed an image extraction method for extracting, from a subject image that records both the background and the object to be extracted, image data of the object using a mask. An initial mask used for extracting the subject region is generated on the basis of difference data between the subject image and the background image that records the background alone, the region of the initial mask is grown on the basis of the similarity between the features of a first region and its neighboring second region in the subject image corresponding to the initial mask, and the image data of the object is extracted from the first image on the basis of the grown mask region.
-
公开(公告)号：US06766055B2
公开(公告)日：2004-07-20
申请号：US10150062
申请日：2002-05-20
IPC分类号： G06K934
CPC分类号： G06K9/48 , G06K9/6203 , G06T7/11 , G06T7/12 , G06T7/174 , G06T7/181 , G06T7/187 , G06T7/194 , G06T2207/10016 , G06T2207/20156 , G06T2207/20224
摘要： This invention relates to an image processing method for precisely and automatically recognizing a specific image extraction region to be divided from an input image, and extracting the specific image extraction region. Thresholding is done for intensity differences of edge data obtained from the input data to extract difference edge data. A main extraction region is estimated from the outermost contour line extracted based on the extraction result of the difference edge data. Thresholding or the like is done in units of pixels of the input image to extract an initial region. Extraction region determination processing is done for extracting an accurate target region by combining the main extraction region and initial region.
摘要翻译： 本发明涉及一种用于精确自动识别要从输入图像中划分的特定图像提取区域并提取特定图像提取区域的图像处理方法。 对从输入数据获得的边缘数据的强度差进行阈值处理，以提取差分边缘数据。 基于差分边缘数据的提取结果，从提取的最外层轮廓线估计主提取区域。 以输入图像的像素为单位进行阈值化等，以提取初始区域。 通过组合主提取区域和初始区域来提取精确目标区域的提取区域确定处理。
-
公开(公告)号：US06453069B1
公开(公告)日：2002-09-17
申请号：US08972166
申请日：1997-11-17
IPC分类号： G06K948
CPC分类号： G06K9/48 , G06K9/6203 , G06T7/11 , G06T7/12 , G06T7/174 , G06T7/181 , G06T7/187 , G06T7/194 , G06T2207/10016 , G06T2207/20156 , G06T2207/20224
摘要： This invention relates to an image processing method for precisely and automatically recognizing a specific image extraction region to be divided from an input image, and extracting the specific image extraction region. Thresholding is done for intensity differences of edge data obtained from the input data to extract difference edge data. A main extraction region is estimated from the outermost contour line extracted based on the extraction result of the difference edge data. Thresholding or the like is done in units of pixels of the input image to extract an initial region. Extraction region determination processing is done for extracting an accurate target region by combining the main extraction region and initial region.
摘要翻译： 本发明涉及一种用于精确自动识别要从输入图像中划分的特定图像提取区域并提取特定图像提取区域的图像处理方法。 对从输入数据获得的边缘数据的强度差进行阈值处理，以提取差分边缘数据。 基于差分边缘数据的提取结果，从提取的最外层轮廓线估计主提取区域。 以输入图像的像素为单位进行阈值化等，以提取初始区域。 通过组合主提取区域和初始区域来提取精确目标区域的提取区域确定处理。
-
公开(公告)号：US06404936B1
公开(公告)日：2002-06-11
申请号：US08989976
申请日：1997-12-12
IPC分类号： G06K920
CPC分类号： G06T7/174 , G06T7/11 , G06T7/187 , G06T7/194 , G06T2207/10016 , G06T2207/20156 , G06T2207/20192
摘要： There is disclosed a method of extracting the region of a subject image from an input image including the subject image. A subject region mask for masking the region of the subject image is generated, and the contour of the subject region mask is shaped. After local regions for correcting the contour shaped by contour shaping are set on the basis of information of the contour of the subject region mask before and after contour shaping, the contour of the shaped subject region mask is corrected within the set local regions.
摘要翻译： 公开了从包括被摄体图像的输入图像中提取被摄体图像的区域的方法。 生成用于遮蔽被摄体图像的区域的被摄体区域掩模，并且对该对象区域掩模的轮廓进行成形。 基于轮廓整形之前和之后的对象区域掩模的轮廓的信息来设置用于校正由轮廓成形形成的轮廓的局部区域之后，在设定的局部区域内校正成形的对象区域掩模的轮廓。
-
公开(公告)号：US6018744A
公开(公告)日：2000-01-25
申请号：US5827
申请日：1998-01-12
申请人： Akira Mamiya , Akira Suga , Hideo Takiguchi , Takashi Aizawa , Fumiaki Takahashi , Kenji Hatori , Koji Hatanaka
发明人： Akira Mamiya , Akira Suga , Hideo Takiguchi , Takashi Aizawa , Fumiaki Takahashi , Kenji Hatori , Koji Hatanaka
CPC分类号： G06F17/30017 , Y10S707/99931 , Y10S707/99943 , Y10S707/99945 , Y10S707/99948
摘要： A method and an apparatus for managing data including images, voice, characters, and the like, in a unified manner. The apparatus has an attribute file or an attribute table for registering therein an attribute peculiar to the data to be registered so that the data attribute can be registered simultaneously with the registration of the data. The data can thus be managed through an application in a unified manner based on the attribute data registered in the attribute file or the attribute table. In order to complete the processing of the application, the attribute data of the attribute file or the attribute table is set to be a mode either of "read-only" or "hidden".
摘要翻译： 以统一的方式管理包括图像，语音，字符等的数据的方法和装置。 该装置具有用于在其中登记要登记的数据特有的属性的属性文件或属性表，使得可以与数据的登记同时登记数据属性。 因此，可以基于登记在属性文件或属性表中的属性数据统一地通过应用程序来管理数据。 为了完成应用程序的处理，将属性文件或属性表的属性数据设置为“只读”或“隐藏”的模式。
-
7.发明授权Multimedia file management in which specialized icons can be created for different file types 失效多媒体文件管理，可以为不同的文件类型创建专门的图标
公开(公告)号：US5680558A
公开(公告)日：1997-10-21
申请号：US354113
申请日：1994-12-06
申请人： Koji Hatanaka , Hideo Takiguchi , Takashi Aizawa , Fumiaki Takahashi , Akira Mamiya , Kenji Hatori
发明人： Koji Hatanaka , Hideo Takiguchi , Takashi Aizawa , Fumiaki Takahashi , Akira Mamiya , Kenji Hatori
CPC分类号： G06F3/04817 , G06F17/30067
摘要： There are disclosed a method and system for managing a file that allows an operator to easily select, specify, and manage a multimedia file (including audio data, text, still image, moving image, etc.) via a display screen. The type of a file is identified. If the file is an audio data file, then an icon is generated with an image representing an amplitude waveform or a frequency distribution waveform of the audio data, or, the icon is generated with an image including a color or a pattern preassigned to the frequency distribution or both. If the file is a text file, then an icon is generated with an image representing an arbitrary area of an arbitrary page of the text file. If the file is a still image file, then an icon is generated with an image obtained by reducing an arbitrary area of the still image. If the file is a moving image file, then an icon is generated with an image obtained by reducing an arbitrary area of an arbitrary scene of the moving image.
摘要翻译： 公开了一种用于管理文件的方法和系统，其允许操作者经由显示屏容易地选择，指定和管理多媒体文件（包括音频数据，文本，静止图像，运动图像等）。 识别文件的类型。 如果文件是音频数据文件，则产生具有表示音频数据的幅度波形或频率分布波形的图像的图标，或者，利用包括预先分配给频率的颜色或图案的图像来生成图标 分配或两者。 如果文件是文本文件，则生成图标，其中图像表示文本文件的任意页面的任意区域。 如果文件是静止图像文件，则通过减少静止图像的任意区域而获得的图像生成图标。 如果文件是运动图像文件，则通过减少运动图像的任意场景的任意区域而获得的图像生成图标。
-
公开(公告)号：US07366360B2
公开(公告)日：2008-04-29
申请号：US11407362
申请日：2006-04-20
申请人： Hideo Takiguchi , Kotaro Yano , Tatsushi Katayama , Fumiaki Takahashi , Kenji Hatori , Koji Hatanaka
发明人： Hideo Takiguchi , Kotaro Yano , Tatsushi Katayama , Fumiaki Takahashi , Kenji Hatori , Koji Hatanaka
IPC分类号： G06K9/36
CPC分类号： G06T3/4038 , H04N1/3876 , H04N5/23238
摘要： An image synthesization method, whereby a plurality of images, each of which has a partially overlapping image area, are synthesized to create a single synthetic image, comprises a determination step of inputting a plurality of image data sets that correspond to the plurality of images that are input, and of determining whether or not an image in the partially overlapping image area of each of images that are indicated by the plurality of image data sets includes mainly characters an image processing step of performing, for the plurality of image data sets that are input, image processing in consonance with a result of a determination performed at the determination step and an image synthesization step of synthesizing images that are indicated by the resultant plurality of image data, for which the image processing has been performed at the image processing step. With this arrangement, a plurality of images can be easily and effectively synthesized.
摘要翻译： 一种图像合成方法，其中合成了具有部分重叠的图像区域的多个图像以产生单个合成图像，所述图像合成方法包括：确定步骤，输入与所述多个图像相对应的多个图像数据集， 并且确定由多个图像数据集指示的每个图像的部分重叠的图像区域中的图像是否主要包括字符，图像处理步骤对于多个图像数据集 输入，与在确定步骤中执行的确定结果相一致的图像处理;以及图像合成步骤，合成在所述图像处理步骤中执行了图像处理的所得到的多个图像数据所指示的图像。 利用这种布置，可以容易且有效地合成多个图像。
-
公开(公告)号：US07085435B2
公开(公告)日：2006-08-01
申请号：US10347317
申请日：2003-01-21
申请人： Hideo Takiguchi , Kotaro Yano , Tatsushi Katayama , Fumiaki Takahashi , Kenji Hatori , Koji Hatanaka
发明人： Hideo Takiguchi , Kotaro Yano , Tatsushi Katayama , Fumiaki Takahashi , Kenji Hatori , Koji Hatanaka
IPC分类号： G06K9/32
CPC分类号： G06T3/4038 , H04N1/3876 , H04N5/23238
摘要： An image synthesization method, whereby a plurality of images, each of which has a partially overlapping image area, are synthesized to create a single synthetic image, comprises a determination step of inputting a plurality of image data sets that correspond to the plurality of images that are input, and of determining whether or not an image in the partially overlapping image area of each of images that are indicated by the plurality of image data sets includes mainly characters an image processing step of performing, for the plurality of image data sets that are input, image processing in consonance with a result of a determination performed at the determination step and an image synthesization step of synthesizing images that are indicated by the resultant plurality of image data, for which the image processing has been performed at the image processing step. With this arrangement, a plurality of images can be easily and effectively synthesized.
-
公开(公告)号：US20060188175A1
公开(公告)日：2006-08-24
申请号：US11407362
申请日：2006-04-20
申请人： Hideo Takiguchi , Kotaro Yano , Tatsushi Katayama , Fumiaki Takahashi , Kenji Hatori , Koji Hatanaka
发明人： Hideo Takiguchi , Kotaro Yano , Tatsushi Katayama , Fumiaki Takahashi , Kenji Hatori , Koji Hatanaka
CPC分类号： G06T3/4038 , H04N1/3876 , H04N5/23238
摘要： An image synthesization method, whereby a plurality of images, each of which has a partially overlapping image area, are synthesized to create a single synthetic image, comprises a determination step of inputting a plurality of image data sets that correspond to the plurality of images that are input, and of determining whether or not an image in the partially overlapping image area of each of images that are indicated by the plurality of image data sets includes mainly characters an image processing step of performing, for the plurality of image data sets that are input, image processing in consonance with a result of a determination performed at the determination step and an image synthesization step of synthesizing images that are indicated by the resultant plurality of image data, for which the image processing has been performed at the image processing step. With this arrangement, a plurality of images can be easily and effectively synthesized.
-
-
-
-
-
-
-
-
-
搜索结果
50 条记录 (耗时 0.022 秒)
